Deep Learning Application for Urban Change Detection from Aerial Images

Urban growth estimation is an essential part of urban planning in order to ensure sustainable regional development. For such purpose, analysis of remote sensing data can be used. The difficulty in analysing a time series of remote sensing data lies in ensuring that the accuracy stays stable in different periods. In this publication, aerial images were analysed for three periods, which lasted for 9 years. The main issues arose due to the different quality of images, which lead to bias between periods. Consequently, this results in difficulties in interpreting whether the urban growth actually happened, or it was identified due to the incorrect segmentation of images. To overcome this issue, datasets were generated to train the convolutional neural network (CNN) and transfer learning technique has been applied. Finally, the results obtained with the created CNN of different periods enable to implement different approaches to detect, analyse and interpret urban changes for the policymakers and investors on different levels as a map, grid, or contour map.